Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for N. Asokan

Real-time Attacks Against Deep Reinforcement Learning Policies


Jun 16, 2021
Buse G. A. Tekgul, Shelly Wang, Samuel Marchal, N. Asokan

* 10 pages, 3 figures 

  Access Paper or Ask Questions

Good Artists Copy, Great Artists Steal: Model Extraction Attacks Against Image Translation Generative Adversarial Networks


Apr 26, 2021
Sebastian Szyller, Vasisht Duddu, Tommi Gröndahl, N. Asokan

* 9 pages, 7 figures 

  Access Paper or Ask Questions

A little goes a long way: Improving toxic language classification despite data scarcity


Sep 25, 2020
Mika Juuti, Tommi Gröndahl, Adrian Flanagan, N. Asokan

* Accepted for publication in Findings of ACL: EMNLP 2020 

  Access Paper or Ask Questions

WAFFLE: Watermarking in Federated Learning


Aug 17, 2020
Buse Gul Atli, Yuxi Xia, Samuel Marchal, N. Asokan

* 15 pages, 10 figures, 13 tables 

  Access Paper or Ask Questions

Extraction of Complex DNN Models: Real Threat or Boogeyman?


Oct 11, 2019
Buse Gul Atli, Sebastian Szyller, Mika Juuti, Samuel Marchal, N. Asokan

* 8 pages, 2 figures 

  Access Paper or Ask Questions

DAWN: Dynamic Adversarial Watermarking of Neural Networks


Jun 12, 2019
Sebastian Szyller, Buse Gul Atli, Samuel Marchal, N. Asokan

* 16 pages, 5 figures 

  Access Paper or Ask Questions

Making targeted black-box evasion attacks effective and efficient


Jun 08, 2019
Mika Juuti, Buse Gul Atli, N. Asokan

* 12 pages, 10 figures 

  Access Paper or Ask Questions

Effective writing style imitation via combinatorial paraphrasing


May 31, 2019
Tommi Gröndahl, N. Asokan


  Access Paper or Ask Questions

EAT2seq: A generic framework for controlled sentence transformation without task-specific training


Apr 08, 2019
Tommi Gröndahl, N. Asokan

* 32 pages 

  Access Paper or Ask Questions

Text Analysis in Adversarial Settings: Does Deception Leave a Stylistic Trace?


Feb 26, 2019
Tommi Gröndahl, N. Asokan

* 35 pages To appear in ACM Computing Surveys (CSUR) 

  Access Paper or Ask Questions

All You Need is "Love": Evading Hate-speech Detection


Nov 05, 2018
Tommi Gröndahl, Luca Pajola, Mika Juuti, Mauro Conti, N. Asokan

* 11 pages, Proceedings of the 11th ACM Workshop on Artificial Intelligence and Security (AISec) 2018 

  Access Paper or Ask Questions

Stay On-Topic: Generating Context-specific Fake Restaurant Reviews


Jun 28, 2018
Mika Juuti, Bo Sun, Tatsuya Mori, N. Asokan

* 21 pages, 5 figures, 6 tables. Accepted for publication in the European Symposium on Research in Computer Security (ESORICS) 2018 

  Access Paper or Ask Questions